Raw Multi-channel Audio Source Separation Using Multi-resolution Convolutional Auto-encoders

Abstract

Supervised multi-channel audio source separation requires extracting useful spectral, temporal, and spatial features from the mixed signals. The success of many existing systems is therefore largely dependent on the choice of features used for training. In this work, we introduce a novel multi-channel, multi-resolution convolutional auto-encoder neural network that works on raw time-domain signals to determine appropriate multi-resolution features for separating the singing-voice from stereo music. Our experimental results show that the proposed method can achieve multi-channel audio source separation without the need for hand-crafted features or any pre- or post-processing.

Stats

• citations34
• S2 citations—
• github stars0
• HF likes0
• heat score11.58
• arxiv keygrais2018raw

Related papers

• Multi-band Multi-resolution Fully Convolutional Neural Networks For Singing Voice Separation (2019)5.84
• Multi-resolution Fully Convolutional Neural Networks For Monaural Audio Source Separation (2017)8.82
• Voice And Accompaniment Separation In Music Using Self-attention Convolutional Neural Network (2020)0.00
• End-to-end Source Separation With Adaptive Front-ends (2017)12.17
• A Recurrent Encoder-decoder Approach With Skip-filtering Connections For Monaural Singing Voice Separation (2017)9.41
• Audio Source Separation Via Multi-scale Learning With Dilated Dense U-nets (2019)0.00
• Wave-u-net: A Multi-scale Neural Network For End-to-end Audio Source Separation (2018)0.00
• Denoising Auto-encoder With Recurrent Skip Connections And Residual Regression For Music Source Separation (2018)10.35